English

Scaling Point-based Differentiable Rendering for Large-scale Reconstruction

Distributed, Parallel, and Cluster Computing 2025-12-24 v1 Graphics

Abstract

Point-based Differentiable Rendering (PBDR) enables high-fidelity 3D scene reconstruction, but scaling PBDR to high-resolution and large scenes requires efficient distributed training systems. Existing systems are tightly coupled to a specific PBDR method. And they suffer from severe communication overhead due to poor data locality. In this paper, we present Gaian, a general distributed training system for PBDR. Gaian provides a unified API expressive enough to support existing PBDR methods, while exposing rich data-access information, which Gaian leverages to optimize locality and reduce communication. We evaluated Gaian by implementing 4 PBDR algorithms. Our implementations achieve high performance and resource efficiency: across six datasets and up to 128 GPUs, it reduces communication by up to 91% and improves training throughput by 1.50x-3.71x.

Keywords

Cite

@article{arxiv.2512.20017,
  title  = {Scaling Point-based Differentiable Rendering for Large-scale Reconstruction},
  author = {Hexu Zhao and Xiaoteng Liu and Xiwen Min and Jianhao Huang and Youming Deng and Yanfei Li and Ang Li and Jinyang Li and Aurojit Panda},
  journal= {arXiv preprint arXiv:2512.20017},
  year   = {2025}
}

Comments

13 pages main text, plus appendix

R2 v1 2026-07-01T08:37:57.994Z